© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18805
    Prev
    Next
    INDEX
    Explanations

    mentions of contacting or speaking with specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or entities involved in communication or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posted
    -0.73
    WAYS
    -0.69
    ech
    -0.66
    ãĥł
    -0.65
    thood
    -0.63
    days
    -0.63
    atable
    -0.63
    ibaba
    -0.63
    Minecraft
    -0.62
    years
    -0.62
    POSITIVE LOGITS
     editor
    1.07
     superintendent
    1.05
     moderators
    1.04
     Clerk
    1.03
     Director
    1.01
     interviewer
    1.01
     clerk
    1.00
     editors
    0.99
     director
    0.97
     secretary
    0.97
    Activations Density 0.270%

    No Known Activations